Artificial intelligence cleaner and method for operating same

This application is the National Phase of PCT International Application No. PCT/KR2021/018231, filed on Dec. 3, 2021, which is hereby expressly incorporated by reference into the present application.

The present disclosure relates to an artificial intelligence cleaner and a method for operating the same, and more particularly to an artificial intelligence cleaner that modifies a cleaning path by performing path simplification when an abnormal situation occurs during cleaning.

A robot cleaner may refer to a device that automatically cleans a target area to be cleaned by suctioning foreign substances such as dust from a floor while autonomously traveling in the target area without user intervention. The robot cleaner may determine a cleaning path according to a built-in (or embedded) program and may perform cleaning operations while traveling along the determined cleaning path.

In general, the robot cleaner may consider only the environment within a preset radius (e.g., a radius of 25 cm) from the robot cleaner itself without considering the entire cleaning area, and at the same time may perform cleaning while avoiding obstacles present in the preset radius range. Therefore, the robot cleaner may perform a wandering motion each time it cleans areas it has previously wandered into, such as areas where a long cleaning time has been required to perform cleaning or areas where the robot cleaner has repeatedly collided with obstacles. For example, in a target area with many obstacles, there may occur an example case in which a long time is required to clean the target area or movement of the robot cleaner traveling in the target area is restricted and locked. Additionally, when cleaning a specific area, the robot cleaner may clean the specific area while moving many more times within the specific area than in other areas.

Therefore, if a cleaning path or a cleaning mode suitable for a given cleaning area can be set, the robot cleaner can more efficiently perform such cleaning.

The present disclosure aims to solve the above-described problems and other problems.

An object of the present disclosure is to provide an artificial intelligence cleaner that modifies (or changes) a cleaning path by simplifying the cleaning path when an abnormal situation occurs while cleaning a target area, and a method for operating the same.

An object of the present disclosure is to provide an artificial intelligence cleaner that identifies at least one candidate area in which path simplification is possible and modifies (or changes) a cleaning path by performing path simplification based on the importance of the at least one candidate area, and a method for operating the same.

In accordance with one aspect of the present disclosure, an artificial intelligence cleaner may include: a memory configured to store a simultaneous localization and mapping (SLAM) map of a cleaning space to be cleaned: a travel driver configured to drive the artificial intelligence cleaner; and a processor configured to determine a cleaning path of the artificial intelligence cleaner based on the SLAM map, and to control the travel driver according to the determined cleaning path, wherein, when an abnormal situation occurs during cleaning based on the determined cleaning path, the processor is configured to modify the cleaning path by applying path simplification to a preset area from among the remaining cleaning areas.

The processor may be configured to: identify at least one candidate area where path simplification is possible from among the remaining cleaning areas: determine a priority of the at least one candidate area; and determine the preset area based on the priority level.

The path simplification may be sequentially applied to the candidate areas arranged in ascending priority order such that the path simplification is first applied to a lowest-priority candidate area and is finally applied to a highest-priority candidate area.

The priority may be determined based on the number of vertices compared to a preset area based on the SLAM map.

The processor may be configured to predict a cleaning completion time compared to the remaining cleaning areas based on the modified cleaning path.

The processor may be configured to predict the cleaning completion time based on a reduced number of wheel rotations, after completion of the path simplification.

The abnormal situation may indicate a situation in which a remaining battery lifespan of the artificial intelligence cleaner is considered insufficient, wherein the processor is configured to calculate an insufficient operable time compared to the remaining cleaning areas based on the remaining battery lifespan.

The processor may be configured to: input the cleaning path, the SLAM map, and a cleaning history to an area segmentation model trained using a machine learning algorithm or a deep learning algorithm, and thus obtain map data as a result of the input; and modify the cleaning path using the obtained map data, wherein the trained area segmentation model includes an artificial neural network.

In accordance with another aspect of the present disclosure, a method for operating an artificial intelligence cleaner may include: collecting a plurality of cleaning histories for a cleaning space: dividing the cleaning space into a plurality of cleaning areas using a simultaneous localization and mapping (SLAM) map of the cleaning space and the plurality of collected cleaning histories: determining a cleaning path of the artificial intelligence cleaner in consideration of the divided cleaning areas: controlling a travel driver that drives the artificial intelligence cleaner according to the determined cleaning path; and when an abnormal situation occurs during cleaning based on the determined cleaning path, modifying the cleaning path by applying path simplification to a preset area from among the remaining cleaning areas.

In accordance with another aspect of the present disclosure, a recording medium storing a program required to perform a method of operating an artificial intelligence cleaner may include: performing the method of operating the artificial intelligence cleaner. The method of operating the artificial intelligence cleaner may include: collecting a plurality of cleaning histories for a cleaning space: dividing the cleaning space into a plurality of cleaning areas using a simultaneous localization and mapping (SLAM) map of the cleaning space and the plurality of collected cleaning histories: determining a cleaning path of the artificial intelligence cleaner in consideration of the divided cleaning areas: controlling a travel driver that drives the artificial intelligence cleaner according to the determined cleaning path; and when an abnormal situation occurs during cleaning based on the determined cleaning path, modifying the cleaning path by applying path simplification to a preset area from among the remaining cleaning areas.

The effects of the artificial intelligence cleaner and the operation method of the artificial intelligence cleaner according to the embodiments of the present disclosure will be described as follows.

The artificial intelligence cleaner according to the embodiments of the present disclosure may intelligently adjust detailed cleaning paths according to abnormal situations while minimizing user intervention, and may thus increase usability and convenience of a user based on the result of such adjustment.

Description will now be given in detail according to exemplary embodiments disclosed herein, with reference to the accompanying drawings. For the sake of brief description with reference to the drawings, the same or equivalent components may be provided with the same reference numbers, and description thereof will not be repeated. In general, a suffix such as “module” and “unit” may be used to refer to elements or components. Use of such a suffix herein is merely intended to facilitate description of the specification, and the suffix itself is not intended to give any special meaning or function. In the present disclosure, that which is well-known to one of ordinary skill in the relevant art has generally been omitted for the sake of brevity. The accompanying drawings are used to help easily understand various technical features and it should be understood that the embodiments presented herein are not limited by the accompanying drawings. As such, the present disclosure should be construed to extend to any alterations, equivalents and substitutes in addition to those which are particularly set out in the accompanying drawings.

It will be understood that although the terms first, second, etc. may be used herein to describe various elements, these elements should not be limited by these terms. These terms are generally only used to distinguish one element from another.

It will be understood that when an element is referred to as being “connected with” another element, the element may be connected with the other element or intervening elements may also be present. In contrast, when an element is referred to as being “directly connected with” another element, there are no intervening elements present.

Artificial Intelligence (AI) refers to a field that studies artificial intelligence or methodology capable of achieving artificial intelligence. Machine learning refers to a field that defines various problems handled in the AI field and studies methodology for solving the problems.

In addition, AI does not exist on its own, but is rather directly or indirectly related to other fields in computer science. In recent years, there have been numerous attempts to introduce an AI element into various fields of information technology to use AI to solve problems in those fields.

Machine learning is an area of AI including the field of study that assigns the capability to learn to a computer without being explicitly programmed.

Specifically, machine learning may be a technology for researching and constructing a system for learning based on empirical data, performing prediction, and improving its own performance and researching and constructing an algorithm for the system. Algorithms of machine learning take a method of constructing a specific model in order to derive prediction or determination based on input data, rather than performing strictly defined static program instructions.

The term machine learning may be used interchangeably with the term machine learning.

Numerous machine learning algorithms have been developed in relation to how to classify data in machine learning. Representative examples of such machine learning algorithms include a decision tree, a Bayesian network, a support vector machine (SVM), and an artificial neural network (ANN).

The decision tree refers to an analysis method that plots decision rules on a tree-like graph to perform classification and prediction.

The Bayesian network is a model that represents the probabilistic relationship (conditional independence) between a plurality of variables in a graph structure. The Bayesian network is suitable for data mining through unsupervised learning.

The SVM is a supervised learning model for pattern recognition and data analysis, mainly used in classification and regression analysis.

The ANN is a data processing system in which a plurality of neurons, referred to as nodes or processing elements, is interconnected in layers, as a model of the interconnection relationship between the operation principle of biological neurons and neurons.

The ANN is a model used in machine learning and includes a statistical learning algorithm inspired by a biological neural network (particularly, the brain in the central nervous system of an animal) in machine learning and cognitive science.

Specifically, the ANN may mean a model having a problem-solving ability by changing the strength of connection of synapses through learning at artificial neurons (nodes) forming a network by connecting synapses.

The term ANN may be used interchangeably with the term neural network.

The ANN may include a plurality of layers, each including a plurality of neurons. In addition, the ANN may include synapses connecting neurons.

The ANN may be generally defined by the following three factors: (1) a connection pattern between neurons of different layers: (2) a learning process that updates the weight of a connection; and (3) an activation function for generating an output value from a weighted sum of inputs received from a previous layer.

The ANN includes, without being limited to, network models such as a deep neural network (DNN), a recurrent neural network (RNN), a bidirectional recurrent deep neural network (BRDNN), a multilayer perceptron (MLP), and a convolutional neural network (CNN).

The term “layer” may be used interchangeably with the term “tier” in this specification.

The ANN is classified as a single-layer neural network or a multilayer neural network according to the number of layers.

A general single-layer neural network includes an input layer and an output layer.

In addition, a general multilayer neural network includes an input layer, one or more hidden layers, and an output layer.

The input layer is a layer that accepts external data. The number of neurons of the input layer is equal to the number of input variables. The hidden layer is disposed between the input layer and the output layer. The hidden layer receives a signal from the input layer and extract characteristics. The hidden layer transfers the characteristics to the output layer. The output layer receives a signal from the hidden layer and outputs an output value based on the received signal. Input signals of neurons are multiplied by respective strengths (weights) of connection and then are summed. If the sum is larger than a threshold of the neuron, the neuron is activated to output an output value obtained through an activation function.

The DNN including a plurality of hidden layers between an input layer and an output layer may be a representative ANN for implementing deep learning which is machine learning technology.

The present disclosure may employ the term “deep learning.”

The ANN may be trained using training data. Herein, training may mean a process of determining parameters of the ANN using training data for the purpose of classifying, regressing, or clustering input data. Representative examples of the parameters of the ANN may include a weight assigned to a synapse or a bias applied to a neuron.

The ANN trained by the training data may classify or cluster input data according to the pattern of the input data.

Meanwhile, the ANN trained using the training data may be referred to as a trained model in the present specification.

Next, a learning method of the ANN will be described.